Syscall
|---------------------------------------------------| |---------------------------------------------------| | |----------------------| |----------------------| | | |----------------------| |----------------------| | | | | | | | | | | | | | | | | | | | | | | | | | | | read ---------------> read API --------------> syscall ------------> sys_read | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |----------------------| |----------------------| | | |----------------------| |----------------------| | | App C lib | | syscall layer read operation | |---------------------------------------------------| |---------------------------------------------------| 用户空间 内核空间
除异常和陷入外,它是用户空间访问内核空间的唯一合法入口(dev/proc/sys文件系统均通过syscall实现)。
1 系统调用机制
1) 系统调用号
每个系统调用有唯一且不可回收的系统调用号。
其中arm进入内核态是通过SWI指令(USR-->SVC)实现的, 详见《ARM Architecture Reference Manual》
A2.6.4 Software Interrupt exception(S3C2440 属于ARM9TDMI ARMv4T)。
R14_svc = address of next instruction after the SWI instruction SPSR_svc = CPSR CPSR[4:0] = 0b10011 /* Enter Supervisor mode */ CPSR[5] = 0 /* Execute in ARM state */ /* CPSR[6] is unchanged */ CPSR[7] = 1 /* Disable normal interrupts */ /* CPSR[8] is unchanged */ CPSR[9] = CP15_reg1_EEbit /* Endianness on exception entry */ if high vectors configured then PC = 0xFFFF0008 else PC = 0x00000008
To return after performing the SWI operation, use the following instruction to restore the PC (from R14_svc) and CPSR (from SPSR_svc) and return to the instruction following the SWI: MOVS PC,R14
arch/arm/kernel/calls.S
/* 0 */ CALL(sys_restart_syscall) CALL(sys_exit) CALL(sys_fork_wrapper) CALL(sys_read) CALL(sys_write) /* 5 */ CALL(sys_open)
2)调用号和参数传递
关于如何传递对应的参数 struct pt_regs *regs,如何从C中调用汇编,会在Compliers中讨论。
arch/arm/include/asm/ptrace.h
/* * This struct defines the way the registers are stored on the * stack during a system call. Note that sizeof(struct pt_regs) * has to be a multiple of 8. */ struct pt_regs { long uregs[18]; }; #define ARM_cpsr uregs[16] #define ARM_pc uregs[15] #define ARM_lr uregs[14] #define ARM_sp uregs[13] #define ARM_ip uregs[12] #define ARM_fp uregs[11] #define ARM_r10 uregs[10] #define ARM_r9 uregs[9] #define ARM_r8 uregs[8] #define ARM_r7 uregs[7] #define ARM_r6 uregs[6] #define ARM_r5 uregs[5] #define ARM_r4 uregs[4] #define ARM_r3 uregs[3] #define ARM_r2 uregs[2] #define ARM_r1 uregs[1] #define ARM_r0 uregs[0] #define ARM_ORIG_r0 uregs[17]
arch/arm/kernel/entry-common.S
这个R0是struct pt_regs *regs?自己没看明白,希望哪位大侠告知下 (ATPCS)
entry-header.S (arch\arm\kernel):#define S_OFF 8
sys_fork_wrapper: add r0, sp, #S_OFF b sys_fork
2 系统调用实现(策略)
arch/arm/kernle/sys_arm.c
/* Fork a new task - this creates a new program thread. * This is called indirectly via a small wrapper */ asmlinkage int sys_fork(struct pt_regs *regs) { #ifdef CONFIG_MMU return do_fork(SIGCHLD, regs->ARM_sp, regs, 0, NULL, NULL); #else /* can not support in nommu mode */ return(-EINVAL); #endif }
kernel/fork.c
/* * Ok, this is the main fork-routine. * * It copies the process, and if successful kick-starts * it and waits for it to finish using the VM if required. */ long do_fork(unsigned long clone_flags, unsigned long stack_start, struct pt_regs *regs, unsigned long stack_size, int __user *parent_tidptr, int __user *child_tidptr) { struct task_struct *p; int trace = 0; long nr; /* * Do some preliminary argument and permissions checking before we * actually start allocating stuff */ if (clone_flags & CLONE_NEWUSER) { if (clone_flags & CLONE_THREAD) return -EINVAL; /* hopefully this check will go away when userns support is * complete */ if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) || !capable(CAP_SETGID)) return -EPERM; } /* * We hope to recycle these flags after 2.6.26 */ if (unlikely(clone_flags & CLONE_STOPPED)) { static int __read_mostly count = 100; if (count > 0 && printk_ratelimit()) { char comm[TASK_COMM_LEN]; count--; printk(KERN_INFO "fork(): process `%s' used deprecated " "clone flags 0x%lx\n", get_task_comm(comm, current), clone_flags & CLONE_STOPPED); } } /* * When called from kernel_thread, don't do user tracing stuff. */ if (likely(user_mode(regs))) trace = tracehook_prepare_clone(clone_flags); p = copy_process(clone_flags, stack_start, regs, stack_size, child_tidptr, NULL, trace); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. */ if (!IS_ERR(p)) { struct completion vfork; trace_sched_process_fork(current, p); nr = task_pid_vnr(p); if (clone_flags & CLONE_PARENT_SETTID) put_user(nr, parent_tidptr); if (clone_flags & CLONE_VFORK) { p->vfork_done = &vfork; init_completion(&vfork); } audit_finish_fork(p); tracehook_report_clone(regs, clone_flags, nr, p); /* * We set PF_STARTING at creation in case tracing wants to * use this to distinguish a fully live task from one that * hasn't gotten to tracehook_report_clone() yet. Now we * clear it and set the child going. */ p->flags &= ~PF_STARTING; if (unlikely(clone_flags & CLONE_STOPPED)) { /* * We'll start up with an immediate SIGSTOP. */ sigaddset(&p->pending.signal, SIGSTOP); set_tsk_thread_flag(p, TIF_SIGPENDING); __set_task_state(p, TASK_STOPPED); } else { wake_up_new_task(p, clone_flags); } tracehook_report_clone_complete(trace, regs, clone_flags, nr, p); if (clone_flags & CLONE_VFORK) { freezer_do_not_count(); wait_for_completion(&vfork); freezer_count(); tracehook_report_vfork_done(p, nr); } } else { nr = PTR_ERR(p); } return nr; }